© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 24094
    Prev
    Next
    INDEX
    Explanations

    phrases denoting causation or consequences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "resulted in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Link
    -0.75
    men
    -0.63
    wine
    -0.63
    ened
    -0.63
    lite
    -0.63
    link
    -0.63
    STER
    -0.62
     vulner
    -0.60
    ickr
    -0.60
    externalActionCode
    -0.60
    POSITIVE LOGITS
    escap
    0.90
    ordinate
    0.85
    clusions
    0.83
     lieu
    0.77
    mobi
    0.73
    mediate
    0.73
    animate
    0.73
    pletion
    0.71
    efficiency
    0.71
     vitro
    0.70
    Activations Density 0.070%

    No Known Activations